Lead GenAI Engineer — GCP & Enterprise LLMs

Valiant Technologies LLC; Minneapolis (MN); In loco; USD 77.000 - 110.000; Tempo pieno

Descrizione del lavoro

Valiant Technologies LLC seeks a Lead Software Engineer focused on GenAI and GCP to build enterprise-grade AI solutions. You will design, develop, and deploy LLM-based apps, implement RAG workflows, and optimize performance across cloud platforms.

The role requires hands-on Python expertise, experience with Vertex AI and DocAI, and strong NLP/DL fundamentals. Candidates should be familiar with embeddings, vector databases, and REST services for scalable production deployments.

Competenze

• Hands-on experience with Python and ML frameworks.
• Experience with Vertex AI and Document AI (DocAI).
• Strong NLP, ML, and DL fundamentals; PyTorch preferred.
• Experience with OpenAI APIs and open-source LLMs.
• Familiarity with embedding models, vector databases, and semantic search.

Mansioni

• Design, develop, and implement enterprise-grade Generative AI solutions.
• Build RAG-based applications using retrieval, embeddings and vectors.
• Develop Agentic AI workflows using LangGraph, CrewAI or similar frameworks.
• Fine-tune, deploy and optimize LLMs for performance and scalability.
• Create intelligent document processing solutions with OCR and DocAI.
• Work with Python, FastAPI/Flask to build robust REST services.
• Leverage cloud platforms (GCP/AWS/Azure) for production-grade deployments.
• Ensure scalable, reliable AI applications for enterprise use cases.

Conoscenze

Python

Vertex AI

Document AI

NLP

ML

Deep Learning

PyTorch

LLMs

Embedding models

Vector databases

FastAPI

Flask

REST APIs

Docker

GCP

AWS

Azure

LangGraph

CrewAI

Strumenti

Google Vertex AI

Google Document AI

LangGraph

CrewAI

Docker

REST APIs

FastAPI

Flask

Descrizione del lavoro

Valiant Technologies LLC seeks a Lead Software Engineer focused on GenAI and GCP to build enterprise-grade AI solutions. You will design, develop, and deploy LLM-based apps, implement RAG workflows, and optimize performance across cloud platforms.

The role requires hands-on Python expertise, experience with Vertex AI and DocAI, and strong NLP/DL fundamentals. Candidates should be familiar with embeddings, vector databases, and REST services for scalable production deployments.